CN114882883A

CN114882883A - Intelligent equipment control method, device and system

Info

Publication number: CN114882883A
Application number: CN202210606308.5A
Authority: CN
Inventors: 张新星; 陈峰峰; 高向军; 邓宏; 杨培海; 陈良; 李晓彦; 聂红雁
Original assignee: Sichuan Hongmei Intelligent Technology Co Ltd
Current assignee: Hefei Changhong Meiling Life Electric Appliance Co ltd
Priority date: 2022-05-31
Filing date: 2022-05-31
Publication date: 2022-08-09
Anticipated expiration: 2042-05-31
Also published as: CN114882883B

Abstract

The invention provides an intelligent device control method, device and system. The method comprises the following steps: acquiring a voice instruction input by a user; inputting the voice command into a pre-trained classifier, and determining a command category corresponding to the voice command; determining intelligent equipment to be controlled according to the instruction category; and controlling the intelligent equipment to be controlled through the voice instruction. The scheme of the invention can solve the problems of poor flexibility and low efficiency when the intelligent equipment performs voice control.

Description

Intelligent equipment control method, device and system

Technical Field

The invention relates to the technical field of equipment control, in particular to an intelligent equipment control method, device and system.

Background

Along with the progress of the technology, various intelligent devices integrated with intelligent functions appear in the visual field of people, and the intelligent devices can also perform information interaction with users and realize various intelligent functions besides realizing the original basic functions, thereby facilitating the life of people.

In the process of using the intelligent device, for convenience of operation, a user can control the intelligent device through voice, namely, the user sends a control instruction through a voice mode, and the intelligent device receives and executes the voice instruction. However, the intelligent device can only be controlled by sending the voice command, which causes the problems of poor flexibility and low efficiency when the intelligent device is controlled by voice.

Accordingly, a new smart device control method is required to solve the above-mentioned problems.

Disclosure of Invention

The embodiment of the invention provides a method, a device and a system for controlling intelligent equipment, which are used for solving the problems of poor flexibility and low efficiency when the intelligent equipment performs voice control.

In a first aspect, an embodiment of the present invention provides an intelligent device control method, which is applied to an intelligent device control apparatus, where the intelligent device control apparatus is disposed in a first intelligent device and is in communication connection with at least one second intelligent device, and the method includes:

acquiring a voice instruction input by a user;

inputting the voice command into a pre-trained classifier, and determining a command category corresponding to the voice command;

determining intelligent equipment to be controlled according to the instruction category;

and controlling the intelligent equipment to be controlled through the voice instruction.

Optionally, the instruction categories include: general instructions, special instructions, and invalid instructions; the general instruction represents an instruction executable by any intelligent device, and the special instruction corresponds to an intelligent device capable of executing the special instruction;

correspondingly, the step of determining the intelligent equipment to be controlled according to the instruction category comprises the following steps:

when the instruction type is the general instruction, determining that the first intelligent device is the intelligent device to be controlled;

when the instruction type is the exclusive instruction, determining whether the exclusive instruction corresponds to the first intelligent device, if so, determining that the first intelligent device is the intelligent device to be controlled, and if not, determining the intelligent device to be controlled from at least one second intelligent device;

and when the instruction type is the invalid instruction, ending the current flow.

Optionally, determining the smart device to be controlled from at least one second smart device includes:

determining whether at least one third intelligent device corresponding to the dedicated instruction exists in at least one second intelligent device in a control group where the first intelligent device is located, wherein the control group comprises the first intelligent device and at least one second intelligent device meeting a preset grouping condition;

determining a number of the third smart devices when the third smart device is present within the control group;

when the number of the third intelligent equipment is 1, determining that the third intelligent equipment is the intelligent equipment to be controlled;

when the number of the third intelligent devices is a positive integer greater than 1, determining the intelligent device to be controlled from at least one third intelligent device;

and when the third intelligent device does not exist in the control group, determining the intelligent device to be controlled from the second intelligent devices outside the control group.

Optionally, determining the to-be-controlled smart device from at least one third smart device includes:

determining whether the voice instruction comprises a device name of the intelligent device;

when the voice instruction comprises the equipment name, taking a third intelligent equipment corresponding to the equipment name as the intelligent equipment to be controlled;

when the voice instruction does not comprise the equipment name, generating prompt information to prompt a user to select an instruction through voice;

and determining the intelligent equipment to be controlled according to the voice selection instruction.

Optionally, when the voice instruction does not include the device name, determining a function type of the dedicated instruction corresponding to the voice instruction;

determining execution priorities of the function categories, wherein each function category corresponds to an execution priority, and the execution priorities comprise intelligent device priorities for executing the exclusive instructions;

and selecting the intelligent equipment to be controlled from the third intelligent equipment according to the execution priority.

Optionally, the classifier is trained by:

acquiring a general instruction sample set and an exclusive instruction sample set; the special instruction sample set comprises at least one characteristic data corresponding to a special instruction;

training the classifier by utilizing a general instruction sample set and a special instruction sample set; wherein, when the general instruction sample set is used as the input of the classifier, a general instruction is used as the output of the classifier; when the exclusive instruction sample set is used as the input of the classifier, an exclusive instruction is used as the output of the classifier.

In a second aspect, an embodiment of the present invention provides an intelligent device control apparatus, including:

the acquisition unit is used for acquiring a voice instruction input by a user;

the instruction type determining unit is used for inputting the voice instruction into a pre-trained classifier and determining an instruction type corresponding to the voice instruction;

the equipment determining unit is used for determining intelligent equipment to be controlled according to the instruction type;

and the control unit is used for controlling the intelligent equipment to be controlled through the voice instruction.

Optionally, when the instruction category includes: the device comprises a general instruction, an exclusive instruction and an invalid instruction, wherein the general instruction represents an instruction executable by any intelligent device, and when the exclusive instruction corresponds to an intelligent device capable of executing the exclusive instruction, the device determining unit is used for executing:

Optionally, when the device determining unit determines the to-be-controlled smart device from at least one second smart device, the device determining unit specifically performs:

Optionally, when the device determining unit determines the to-be-controlled smart device from at least one third smart device, the device determining unit specifically performs:

In a third aspect, an embodiment of the present invention provides an intelligent device control system, including: the intelligent control device is arranged in the first intelligent equipment and is in communication connection with at least one second intelligent equipment;

the intelligent device control apparatus is configured to execute the method in any of the above embodiments.

Optionally, the apparatus further comprises: a voice recognition device;

the voice recognition device is in communication connection with the intelligent equipment control device;

the voice recognition device is used for recognizing the voice information of the user and converting the voice information into a voice command.

Optionally, the apparatus further comprises: a control group dividing means;

the control group dividing device is used for dividing at least one intelligent device which meets a preset grouping condition into control groups.

Optionally, the control group dividing device is configured to calculate a grouping score of at least one of the intelligent devices according to the preset grouping condition, and divide at least one of the intelligent devices having a score within a preset range into one control group.

Optionally, the apparatus further comprises: a classifier training unit;

and the classifier training device is used for training the classifier through the general instruction sample set and the special instruction sample set.

The embodiment of the invention provides an intelligent device control method, an intelligent device control device and an intelligent device control system. The scheme provided by each embodiment of the invention not only can classify the voice command, but also can select different intelligent equipment to be controlled according to the voice command, so that the voice command does not only correspond to single equipment, but also can control different intelligent equipment according to requirements, and the intelligent equipment is more flexibly controlled and has higher efficiency.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a flowchart of a method for controlling an intelligent device according to an embodiment of the present invention;

fig. 2 is a flowchart of a method for determining an intelligent device to be controlled according to an embodiment of the present invention;

FIG. 3 is a flowchart of a method for training a classifier according to an embodiment of the present invention;

fig. 4 is a schematic diagram of an intelligent device control apparatus according to an embodiment of the present invention;

fig. 5 is a schematic diagram of an intelligent device control system according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.

With the progress of the technology, the intelligent equipment is increased along with the concept of smart home finished products. The intelligent device can also perform information interaction with the user besides realizing the original functions, thereby facilitating the life of people.

In the process of using the intelligent device, for convenience of operation, the user can control the intelligent device through voice, that is, the user sends a control instruction through voice. However, the intelligent device is controlled by the voice sending instruction and can only send the voice instruction to the single intelligent device, so that the problems of poor flexibility and low efficiency of the intelligent device during voice control are caused.

The following describes the method, apparatus and system for controlling an intelligent device according to the present invention in detail through various embodiments.

As shown in fig. 1, an embodiment of the present invention provides an intelligent device control method, which may include the following steps:

step 110: and acquiring a voice instruction input by a user.

Step 120: and inputting the voice command into a pre-trained classifier, and determining a command class corresponding to the voice command.

Step 130: and determining the intelligent equipment to be controlled according to the instruction category.

Step 140: and controlling the intelligent equipment to be controlled through the voice instruction.

Specifically, after a user sends a voice command through voice, the voice command is troublesome and is recognized through a classifier, the semantics of the voice command are classified, the command category of the voice command is determined, different command categories may be applicable to different intelligent devices, so that the intelligent device to be controlled applicable to the command category needs to be determined first, and the control requirement of the voice command is realized through the intelligent device to be controlled.

In one embodiment of the invention, the instruction classes include: general instructions, special instructions, and invalid instructions; the general instruction represents an instruction executable by any intelligent device, and the special instruction corresponds to an intelligent device capable of executing the special instruction. Accordingly, as shown in fig. 2, an embodiment of the present invention provides a method for determining an intelligent device to be controlled, where the method may include the following steps:

step 210: and when the instruction type is the general instruction, determining that the first intelligent equipment is the intelligent equipment to be controlled.

Step 220: when the instruction type is the exclusive instruction, determining whether the exclusive instruction corresponds to the first intelligent device, if so, determining that the first intelligent device is the intelligent device to be controlled, and if not, determining the intelligent device to be controlled from at least one second intelligent device.

Step 230: and when the instruction type is the invalid instruction, ending the current flow.

Specifically, the general instruction is a function that can be executed by different intelligent devices, and the general instruction is independent of the specific function of the intelligent device, and can be realized by simple processing, such as a weather inquiry function, and can be realized by intelligent devices such as a television, an air conditioner, a refrigerator and the like, and the current weather is inquired by a voice instruction, and the intelligent device is not required to execute the specific function. For example, a voice instruction "how is the current weather" is sent to the intelligent refrigerator, and at this moment, the intelligent refrigerator can be used as the intelligent device to be controlled, and the intelligent refrigerator obtains the current weather condition through the internet. The dedicated instruction is an instruction that can be executed by a specific intelligent device, and usually the dedicated instruction needs to use a specific function of the intelligent device, for example, a voice instruction is that "i feel a little hot", and a corresponding dedicated instruction should be executed by an intelligent air conditioner for reducing the indoor temperature. If first smart machine is intelligent air conditioner, then first smart machine is direct as the smart machine that waits to control, if first smart machine is not intelligent air conditioner, for intelligent refrigerator, the unable execution of intelligent refrigerator reduces the instruction of indoor temperature, consequently need follow the second smart machine and confirm intelligent air conditioner, regard as the smart machine that waits to control with intelligent air conditioner. When the instruction class cannot be recognized from the voice instruction, the explanation may be that other voices are mistaken as the voice instruction or the semantics of the voice instruction are not smooth, in which case no action is performed in order to reduce the misoperation.

In an embodiment of the present invention, determining the to-be-controlled smart device from at least one second smart device includes: determining whether at least one third intelligent device corresponding to the dedicated instruction exists in at least one second intelligent device in a control group where the first intelligent device is located, wherein the control group comprises the first intelligent device and at least one second intelligent device meeting a preset grouping condition;

Specifically, the control groups may be divided according to the placement positions of the smart devices and the voice habits of the users, and the smart devices belonging to the same control group may be earlier than the smart devices belonging to other control groups in the corresponding order when receiving the voice command. The control group is marked according to the intelligent device control device receiving the voice command, so that innovative interactive experience can be realized. For example, the intelligent devices in the same bedroom belong to a control group, the voice instruction is used for playing songs, when the first intelligent device does not correspond to the special instruction, the third intelligent device capable of executing the song playing instruction is firstly searched from the control group corresponding to the bedroom, and if 1 intelligent device capable of executing the song playing instruction is placed in the bedroom, the intelligent television can be used as the intelligent device to be controlled. If there are multiple intelligent devices capable of executing the song playing instruction, one of the intelligent devices is selected to execute the song playing instruction. And if the control group corresponding to the bedroom does not comprise the intelligent equipment capable of executing the song playing instruction, selecting the intelligent equipment to be controlled from the intelligent equipment in other rooms.

In an embodiment of the present invention, optionally, the determining, from at least one third smart device, the smart device to be controlled includes:

Specifically, when the user indicates which intelligent device needs to be executed through the voice command, the intelligent device selected by the user may be used as the intelligent device to be controlled to execute the voice command. For example, the voice command input by the user is "living room television plays songs", the control group can be determined through "living room", and the smart television executes the song playing command if the "television" corresponds to the smart television in the control group to which the living room belongs. When the user does not speak the device name in the voice command, a prompt voice can be generated to inquire the intelligent device which the user wants to control, and after the user selects through the voice, the voice command is executed through the intelligent device. In this way, the user can select the intelligent device for executing the voice instruction from the plurality of third intelligent devices capable of executing the voice instruction.

In an embodiment of the present invention, when the voice command does not include the device name, determining a function type of the dedicated command corresponding to the voice command;

Specifically, when the user does not select a specific smart device to execute the voice instruction, the smart device to be controlled may be automatically selected according to a preset execution priority. For example, when the voice command is to play a song, the execution priority for executing the song playing command is determined, for example, the execution priority for playing the song is smart audio-television-smart refrigerator-smart air conditioner (both having a music playing function), that is, when a smart audio is provided outside the control group or the group, the smart audio preferentially executes the song playing command, and when the smart audio is not provided, the music playing command is executed in the order of television-smart refrigerator-smart air conditioner.

As shown in fig. 3, an embodiment of the present invention provides a method for training a classifier, where the method includes the following steps:

step 310: acquiring a general instruction sample set and an exclusive instruction sample set; the general instruction sample set comprises at least one characteristic data corresponding to a general instruction, and the exclusive instruction sample set comprises at least one characteristic data corresponding to an exclusive instruction.

Step 320: training the classifier by utilizing a general instruction sample set and an exclusive instruction sample set; wherein, when the general instruction sample set is used as the input of the classifier, a general instruction is used as the output of the classifier; when the exclusive instruction sample set is used as the input of the classifier, an exclusive instruction is used as the output of the classifier.

Specifically, the classifier is trained by a general instruction sample set and an exclusive instruction sample set through a machine learning method, and aims to generate a classifier with the capability of identifying a target; the CART classification tree algorithm is adopted in the embodiment of the invention to train the data set; taking a cart (classification And Regression tree) decision tree as a Machine learning method, that is, taking a decision tree algorithm with an error function as a kiney coefficient as an example, it should be understood that the embodiment of the present invention may also apply other Machine learning algorithms such as Deep Neural Networks (DNNs), Support Vector Machines (SVMs), And the like.

The flow of the CART classification tree algorithm comprises the following steps:

collecting a large number of feature data sample sets, and marking the category of each feature vector, for example, a general instruction is marked as 1, and an exclusive instruction is-1; and randomly dividing the characteristic data of the marked classes into a verification set and a training set.

In this embodiment, the training set accounts for 90%, and the validation set accounts for 10%;

and training the training set by using a corresponding training method.

In this embodiment, a CART decision tree generation algorithm is used to train a training set to generate a CART decision tree.

And performing post pruning on the decision tree by adopting a decision tree post-pruning algorithm according to the verification set to obtain the classifier.

Specifically, post-pruning (Postpruning) processing is performed on the generated CART decision tree, the Generalization (Generalization) capability of the generated CART decision tree is improved, and the obtained pruned decision tree is the classifier.

It should be understood that, in the embodiment, the CART decision tree and the post-pruning processing are adopted as the training method of the classifier, and a certain proportion of verification sets need to be reserved in the foregoing steps. In other embodiments, such as using Deep Neural Networks (DNNs), Support Vector Machines (SVMs), and other Machine learning algorithms, the validation set may be used as other processing in the training process to reduce generalization errors or to eliminate the need to leave the validation set.

As shown in fig. 4, an embodiment of the present invention provides an intelligent device control apparatus, including:

an obtaining unit 410, configured to obtain a voice instruction input by a user.

The instruction type determining unit 420 is configured to input the voice instruction into a pre-trained classifier, and determine an instruction type corresponding to the voice instruction.

And the device determining unit 430 is configured to determine the intelligent device to be controlled according to the instruction category.

And a control unit 440, configured to control the intelligent device to be controlled through the voice instruction.

Optionally, when the device determining unit 430 determines the to-be-controlled smart device from at least one second smart device, specifically perform:

Optionally, the device determining unit 430 is configured to perform: when the voice instruction does not comprise the equipment name, determining the function type of the exclusive instruction corresponding to the voice instruction;

As shown in fig. 4, the intelligent device control apparatus further includes: a classifier training unit 450;

the splitter training unit 450 is configured to perform:

training the classifier by utilizing a general instruction sample set and an exclusive instruction sample set; wherein, when the general instruction sample set is used as the input of the classifier, a general instruction is used as the output of the classifier; when the exclusive instruction sample set is used as the input of the classifier, an exclusive instruction is used as the output of the classifier.

It is to be understood that the illustrated structure of the embodiment of the present invention does not specifically limit the intelligent device control apparatus. In other embodiments of the invention, the smart device control apparatus may include more or fewer components than shown, or combine certain components, or split certain components, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

Because the information interaction, execution process, and other contents between the units in the device are based on the same concept as the method embodiment of the present invention, specific contents may refer to the description in the method embodiment of the present invention, and are not described herein again.

As shown in fig. 5, an embodiment of the present invention provides an intelligent device control system, including: a smart device control apparatus 510 and at least two smart devices 520.

The smart device control apparatus 510 is configured to perform the method of any of the above embodiments.

As shown in fig. 5, optionally, the system further includes: a speech recognition device 530;

the voice recognition device 530 is in communication connection with the intelligent device control device 510;

the voice recognition device 530 is used for recognizing the voice information of the user and converting the voice information into a voice command.

As shown in fig. 5, optionally, the system further includes: a control group dividing means 540;

the control group dividing device 540 is configured to divide at least one intelligent device that meets a preset grouping condition into control groups.

Optionally, the control group dividing device 540 is configured to calculate a grouping score of at least one of the smart devices according to the preset grouping condition, and divide at least one of the smart devices having a score within a preset range into a control group.

Specifically, according to the voice habit of the user and the placement positions of the devices in the family, when the user initiates awakening, the devices belonging to the same space are closer to the scores obtained by the devices in other spaces, the score intervals of the devices participating in comprehensive election have relevance, and after big data analysis, the voice devices can be grouped and marked according to the virtual space, so that various innovative interactive experiences are supported.

Optionally, the system further includes: a classifier training unit 550;

It should be noted that not all steps and modules in the above flows and system structure diagrams are necessary, and some steps or modules may be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted as required. The system structure described in the above embodiments may be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by a plurality of physical entities, or some components in a plurality of independent devices may be implemented together.

In the above embodiments, the hardware unit may be implemented mechanically or electrically. For example, a hardware element may comprise permanently dedicated circuitry or logic (such as a dedicated processor, FPGA or ASIC) to perform the corresponding operations. The hardware elements may also comprise programmable logic or circuitry, such as a general purpose processor or other programmable processor, that may be temporarily configured by software to perform the corresponding operations. The specific implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.

While the invention has been particularly shown and described with reference to the preferred embodiments and drawings, it is not intended to be limited to the specific embodiments disclosed, and it will be understood by those skilled in the art that various other combinations of code approval means in the various embodiments described above may be utilized to obtain further embodiments of the invention, which are also within the scope of the invention.

Claims

1. The intelligent equipment control method is applied to an intelligent equipment control device, the intelligent equipment control device is arranged in first intelligent equipment and is in communication connection with at least one second intelligent equipment, and the method comprises the following steps:

acquiring a voice instruction input by a user;

2. The method of claim 1, wherein the instruction categories include: general instructions, special instructions, and invalid instructions; the general instruction represents an instruction executable by any intelligent device, and the special instruction corresponds to an intelligent device capable of executing the special instruction;

3. The method according to claim 2, wherein the determining the smart device to be controlled from the at least one second smart device comprises:

4. The method of claim 3, wherein determining the smart device to be controlled from the at least one third smart device comprises:

5. The method of claim 4,

when the voice instruction does not comprise the equipment name, determining the function type of the exclusive instruction corresponding to the voice instruction;

6. The method of claim 2, wherein the classifier is trained by:

training the classifier by utilizing a general instruction sample set and an exclusive instruction sample set; wherein when the general instruction sample set is used as the input of the classifier, a general instruction is used as the output of the classifier; when the exclusive instruction sample set is used as the input of the classifier, an exclusive instruction is used as the output of the classifier.

7. Intelligent equipment controlling means, its characterized in that includes:

the acquisition unit is used for acquiring a voice instruction input by a user;

8. The apparatus of claim 7,

when the instruction category includes: the device comprises a general instruction, an exclusive instruction and an invalid instruction, wherein the general instruction represents an instruction executable by any intelligent device, and when the exclusive instruction corresponds to an intelligent device capable of executing the exclusive instruction, the device determining unit is used for executing:

9. The apparatus according to claim 7, wherein the device determining unit, when performing the determination of the smart device to be controlled from the at least one second smart device, specifically performs:

10. The apparatus according to claim 9, wherein the device determining unit, when performing the determination of the smart device to be controlled from the at least one third smart device, specifically performs:

11. Intelligent equipment control system, its characterized in that includes: the intelligent equipment control device is arranged in the first intelligent equipment and is in communication connection with at least one second intelligent equipment;

the smart device control apparatus for performing the method of any one of claims 1-6.

12. The system of claim 11, further comprising: a voice recognition device; the voice recognition device is in communication connection with the intelligent equipment control device;

13. The system of claim 11, further comprising: a control group dividing means;

14. The system according to claim 13, wherein the control group dividing means is configured to calculate a grouping score of at least one of the intelligent devices according to the preset grouping condition, and divide at least one of the intelligent devices having a score within a preset range into one control group.

15. The system of claim 11, further comprising: a classifier training unit;